Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Thu, 13 Feb 2020 08:46:07 -0800
From:   Matthew Wilcox <willy@infradead.org>
To:     Michal Hocko <mhocko@kernel.org>
Cc:     Cong Wang <xiyou.wangcong@gmail.com>,
        LKML <linux-kernel@vger.kernel.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        linux-mm <linux-mm@kvack.org>, Mel Gorman <mgorman@suse.de>,
        Vlastimil Babka <vbabka@suse.cz>
Subject: Re: [PATCH] mm: avoid blocking lock_page() in kcompactd
Message-ID: <20200213164607.GR7778@bombadil.infradead.org>
References: <CAM_iQpU0p7JLyQ4mQ==Kd7+0ugmricsEAp1ST2ShAZar2BLAWg@mail.gmail.com>
 <20200126233935.GA11536@bombadil.infradead.org>
 <20200127150024.GN1183@dhcp22.suse.cz>
 <20200127190653.GA8708@bombadil.infradead.org>
 <20200128081712.GA18145@dhcp22.suse.cz>
 <20200128083044.GB6615@bombadil.infradead.org>
 <20200128091352.GC18145@dhcp22.suse.cz>
 <20200128104857.GC6615@bombadil.infradead.org>
 <20200128113953.GA24244@dhcp22.suse.cz>
 <20200213074847.GB31689@dhcp22.suse.cz>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20200213074847.GB31689@dhcp22.suse.cz>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Thu, Feb 13, 2020 at 08:48:47AM +0100, Michal Hocko wrote:
> Can we pursue on this please? An explicit NOFS scope annotation with a
> reference to compaction potentially locking up on pages in the readahead
> would be a great start.

How about this (on top of the current readahead series):

diff --git a/mm/readahead.c b/mm/readahead.c
index 29ca25c8f01e..32fd32b913da 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -160,6 +160,16 @@ unsigned long page_cache_readahead_limit(struct address_space *mapping,
 		.nr_pages = 0,
 	};
 
+	/*
+	 * Partway through the readahead operation, we will have added
+	 * locked pages to the page cache, but will not yet have submitted
+	 * them for I/O.  Adding another page may need to allocate
+	 * memory, which can trigger memory migration.	Telling the VM
+	 * we're in the middle of a filesystem operation will cause it
+	 * to not touch file-backed pages, preventing a deadlock.
+	 */
+	unsigned int nofs = memalloc_nofs_save();
+
 	/*
 	 * Preallocate as many pages as we will need.
 	 */
@@ -217,6 +227,7 @@ unsigned long page_cache_readahead_limit(struct address_space *mapping,
 	 */
 	read_pages(&rac, &page_pool);
 	BUG_ON(!list_empty(&page_pool));
+	memalloc_nofs_restore(nofs);
 	return rac.nr_pages;
 }
 EXPORT_SYMBOL_GPL(page_cache_readahead_limit);